Scribd
Upload
184 views8 pages

Project 1 - Radio Link Failure Prediction

(1) This document proposes using historical radio link (RL) performance data and weather forecast data to predict RL failures and assess risks. (2) It describes the training data, which includes preprocessed RL KPI data and time-aligned weather data, and evaluation criteria for machine learning algorithms trained on the data. (3) Students are tasked with using the provided datasets to train an ML algorithm to predict RL performance in new network deployments, and their algorithms will be evaluated based on average error between predictions and actual results.

Uploaded by

Ahmed Belhadj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
184 views8 pages

Project 1 - Radio Link Failure Prediction

(1) This document proposes using historical radio link (RL) performance data and weather forecast data to predict RL failures and assess risks. (2) It describes the training data, which includes preprocessed RL KPI data and time-aligned weather data, and evaluation criteria for machine learning algorithms trained on the data. (3) Students are tasked with using the provided datasets to train an ML algorithm to predict RL performance in new network deployments, and their algorithms will be evaluated based on average error between predictions and actual results.

Uploaded by

Ahmed Belhadj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

Radio Link Failure Prediction

Project for WIN « Wireless Intelligent Networks » students


Proposed by: Jihène Ben Abderrazak

January 2021
Background
Site7

Site6

Site1
Site3 Site2
IP/MPLS Network

Site4

Site5 Site4
Rain, snow, wind, fog, and other weather-related
phenomena affects the performance of radio links
2
Network resiliency against
weather-based disruptions
The impact of weather conditions on wireless channel
quality, is modeled with a specific emphasis on the
structural impact of winds on cellular towers.

Protection strategies were proposed in wireless


networks (mostly, WMNs and FSO network), wired
networks and converged networks.

The importance of these topics is expected to grow in


the next years considering the important role that
wireless links are expected to play in 5G networks
(both in the access and backhaul segments) and the
increasing occurrences of extreme weather conditions
associated to global warming.

Source: M. Tornatore et al., "A survey on network resiliency methodologies against weather-based disruptions," 2016 8th International
Workshop on Resilient Networks Design and Modeling (RNDM), Halmstad, 2016, pp. 23-34, doi: 10.1109/RNDM.2016.7608264. 3
Problem
Given the region-wise, historical data sets on radio
link (RL) performance and weather forecast predict
the RL failures to assess risks.

4
Datasets (1/2)
• Training data includes pre-processed and anonymised RL KPIs from
the networks and time-aligned weather data.
• RL data
– KPI data includes date/time, frequency band, link length, error and failure
statistics, availability ratio, stability score, capacity, modulation (128QAM,
256QAM, 512QAM, …)
• Weather data
– Forecast data includes status, temperatures, humidity, wind speed and
direction for the following 5 days (Recorded twice a day)
– Measurement data includes temperatures, humidity, wind speed and
direction, precipitation and overcast (Recorded hourly)
• Distances
– A matrix that gives distance for weather stations and RL sites
5
Datasets (2/2)

6
Evaluation criteria
• Students must use the provided data set to train a machine
learning algorithm.
• The output of the ML algorithm should be able to predict the
performance obtained in a new network deployment.
• The choice of the ML approach is decided by each group.
• The test dataset will be provided to the students to evaluate the
performance of the proposed algorithms.
• The evaluation of the proposed algorithms will be based on the
average squared-root error obtained along with all the predictions
compared to the actual result in each type of deployment.
7
Thank you
Contact: [email protected]

You might also like